human-feedbacklisted

# Human Feedback Turn a person's reaction to working output into an evidence-backed root cause and a correction made at that root. This skill owns diagnosis, not implementation. ## 1. Enter Two entries: - **Detected:** a person reacts to working code, design, or documentation. Invoke on the reaction itself, before answering it. - **Invited:** verification covers UI or a human-use scenario and the user accepted a feedback pass. Name the real interface and the flows to operate, then collect what the person observed. Route a crash or reproducible failure to `aaaav-do` debugging and a request for new behavior to its implementation path. A reaction with no identifiable target may be venting; ask whether the user wants it investigated. **Complete when:** there is a working code, design, or documentation target the person wants improved. ## 2. Diagnose Attend to the problem the person has, ahead of the fix they propose. Identify separately: - the person's observed experience and the need left unmet - the friction that turns that experience into negative feedback - the behavior, design, or documentation decision that creates the friction - the documented standard, best practice, or project precedent it violates Use `investigating` for substantial cross-source research. If the causal decision and violated standard are unsupported by evidence, classify the reaction as a preference rather than invent a defect. Treat justification added to a response or document as a wor